Dear authors:

Thank you for participating in the Interactive Discussion. As editor of GMD, you will notice that one of the referees judged the submission to be "approved after minor revision" and the other to be "major revision" at this round. Numerous technical aspects are significantly questioned and must be thoroughly addressed.

There are numerous grammatical errors and erroneous words throughout the document, making it difficult to read and understand. I strongly advise the authors to have their manuscript professionally proofread.

Please make attentive adjustments and responses in response to their feedback. In the second round, I will invite them to review your improved manuscript. Thanks.

Best regards,
Xiaomeng Huang
Handling Topical Editor

Dear authors:

Thank you for participating in the Interactive Discussion. You revised the paper to make it more consistent with the arguments of the referee. As GMD's editor, you'll notice that one referee rated the scientific significance as "Fair" and the scientific quality as "Poor." Numerous technical aspects have been raised and must be thoroughly addressed. Several additional comments follow, which I recommend you consider before publishing.

This paper's motivation is unconvincing. Except for comparing and combining two transfer learning strategies for landslide susceptibility modeling, case-based reasoning (CBR) and domain adaptation (DA), the authors have not provided any new methods or made substantive improvements to the existing models. One of the innovations could result from evaluating the potential of transfer learning for landslide susceptibility modeling using CBR and DA techniques to reduce the burden of data collection and labeling. However, as far as I am aware, the following key related works have been proposed in recent years (but are not limited to):
1. Wang, H., Wang, L., and Zhang, L.: Transfer learning improves landslide susceptibility assessment, Gondwana Research, 1-17, https://doi.org/10.1016/j.gr.2022.07.008, 2022.
2. Xu, Q., Ouyang, C., Jiang, T., Yuan, X., Fan, X., and Cheng, D.: MFFENet and ADANet: a robust deep transfer learning method and its application in high precision and fast cross‑scene recognition of earthquake‑induced landslides, Landslides, 19(7), 1617-1647, 2022.
3. Ai, X., Sun, B., and Chen, X.: Construction of small sample seismic landslide susceptibility evaluation model based on Transfer Learning: a case study of Jiuzhaigou earthquake, Bulletin of Engineering Geology and the Environment, 81(3), 116, https://doi.org/10.1007/s10064-022-02601-6, 2022.
4. Qin, S., Guo, X., Sun, J., Qiao, S., Zhang, L., Yao, J., Cheng, Q., and Zhang, Y.: Landslide detection from open satellite imagery using distant domain transfer learning, Remote Sensing, 13(17), 3383, https://doi.org/10.3390/rs13173383, 2021.
5. Liu, D., Li, J., and Fan, F.: Classification of landslides on the southeastern Tibet Plateau based on transfer learning and limited labelled datasets, Remote Sensing Letters, 12(3), 286-295, 2021. 6. Zhu, Q., Chen, L., Hu, H., Pirasteh, S., Li, H., and Xie, X.: Unsupervised Feature Learning to Improve Transferability of Landslide Susceptibility Representations, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13, 3917-3930, 2020.
7. Lu, H., Ma, L., Fu, X., Liu, C., Wang, Z., Tang, M. and Li, N.: Landslides information extraction using object-oriented image analysis paradigm based on deep learning and transfer learning, Remote Sensing, 12(5), 752, https://doi.org/10.3390/rs12050752, 2020.
The author should give a broad discussion on these transfer learning methods applied to landslide susceptibility modelling. And then, the necessity and novelty of this work should be demonstrated by analyzing and summarizing the advantages and disadvantages of these transfer learning methods.

More detailed information, such as novelty, valuable results, and the major limitation of the methodology, should be included in the conclusion. The authors should also suggest several future research directions.

Throughout the paper, English writing should be greatly improved. Some sentences are too complex, and the correct meaning cannot be extracted. Line 25: "Landslide susceptibility refers to..., and to estimating the likely location of future landslides," for example, but there are many more. I strongly advise the authors to  to go over and revise their manuscript.

Please make careful adjustments and responses in response to the above comments for a second look. Thanks.

Best regards,
Xiaomeng Huang
Handling Topical Editor

Dear authors:

My decision on your manuscript is accepted. Congratulations.
You answered every one of my concerns. This study makes a contribution to the application of transfer learning to landslide susceptibility modeling. This paper, I feel, will be of high relevance to the community. Thank you for submitting your work to GMD once more.

Best regards,
Xiaomeng Huang
Handling Topical Editor